Update README.md
c002730 verified
- dataset:
id: Idavidrein/gpqa
task_id: diamond
value:
score: 91.1
date: '2026-04-06'
source:
url: https://tnsaai.com/models/ngen4-pro
name: TNSA NGen-4 Pro Evaluations
- dataset:
id: openai/gsm8k
task_id: gsm8k
value:
score: 99.2
date: '2026-04-06'
source:
url: https://tnsaai.com/models/ngen4-pro
name: TNSA NGen-4 Pro Evaluations
- dataset:
id: SWE-bench/SWE-bench_Verified
task_id: swe_bench_%_resolved
value:
score: 77.3
date: '2026-04-06'
source:
url: https://tnsaai.com/models/ngen4-pro
name: TNSA NGen-4 Pro Evaluations
- dataset:
id: harborframework/terminal-bench-2.0
task_id: terminal_bench
value:
score: 42.3
date: '2026-04-06'
source:
url: https://tnsaai.com/models/ngen4-pro
name: TNSA NGen-4 Pro Evaluations
- dataset:
id: likaixin/ScreenSpot-Pro
task_id: screenspot_pro
value:
score: 72.9
date: '2026-04-06'
source:
url: https://tnsaai.com/models/ngen4-pro
name: TNSA NGen-4 Pro Evaluations